© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89000
    Prev
    Next
    INDEX
    Explanations

    blog posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BEST
    -0.12
     disple
    -0.10
     sic
    -0.09
     Macy
    -0.09
    DT
    -0.09
    MAT
    -0.09
    ackers
    -0.08
    ++++++++++++++++
    -0.08
     Marcos
    -0.08
    RICS
    -0.08
    POSITIVE LOGITS
    active
    0.11
    articles
    0.10
     articles
    0.10
     publication
    0.10
     news
    0.10
     publishing
    0.10
     publications
    0.10
    æĸĩç«ł
    0.10
     rich
    0.09
     refresh
    0.09
    Activations Density 0.001%

    No Known Activations